On the Role of Batch Size in Stochastic Conditional Gradient Methods

Rustem Islamov, Roman Machacek, Aurelien Lucchi +3

We study the role of batch size in stochastic conditional gradient methods under a $\hat{I}¼$-Kurdyka-Łojasiewicz ($\hat{I}¼$-KL) condition. Focusing on momentum-based stochastic conditional…